Add integration of the new heuristics

components/dom_distiller/core/javascript/extract_features.js

Index: components/dom_distiller/core/javascript/extract_features.js
diff --git a/components/dom_distiller/core/javascript/extract_features.js b/components/dom_distiller/core/javascript/extract_features.js
new file mode 100644
index 0000000000000000000000000000000000000000..a454304fbb94ad7ea3a93100136e3680618137b7
--- /dev/null
+++ b/components/dom_distiller/core/javascript/extract_features.js
@@ -0,0 +1,28 @@
+// Copyright 2015 The Chromium Authors. All rights reserved.
+// Use of this source code is governed by a BSD-style license that can be
+// found in the LICENSE file.
+
+(function() {
+  function hasOGArticle() {
+    var elems = document.head.querySelectorAll(
+        'meta[property="og:type"],meta[name="og:type"]');

[nyquist, 2015/04/01 18:12:20]

Nit: Would we need to do anything special if developers write: "OG:TYPE" instead
of "og:type"? I am assuming that's not part of the spec?

[cjhopman, 2015/04/01 20:59:29]

Yeah, we're not really doing this right, but it's the same way we do it in the
is_distillable_page.js.

(really we need to parse out the namespace aliases from the HEAD tag, but we
just assume that people use 'og').

+    for (var i in elems) {
+      if (elems[i].content && elems[i].content.toUpperCase() == 'ARTICLE') {
+        return true;
+      }
+    }
+    return false;
+  }
+
+  var body = document.body;
+  return {

[nyquist, 2015/04/01 18:12:20]

return as stringified to help out our iOS friends?

[cjhopman, 2015/04/01 20:59:29]

Done.

+     'opengraph': hasOGArticle(),
+     'url': document.location.href,
+     'numElements': body.querySelectorAll('*').length,
+     'numAnchors': body.querySelectorAll('a').length,
+     'numForms': body.querySelectorAll('form').length,
+     'innerText': body.innerText,
+     'textContent': body.textContent,

[nyquist, 2015/04/01 18:12:20]

It would be amazing if we at some point would get UMA stats for the calculation
of these core features. The total time would be good; and per feature would be
bestest.

[cjhopman, 2015/04/01 20:59:29]

Yeah, it would be nice.

+     'innerHTML': body.innerHTML,
+  }
+})()